Papers
arxiv:2110.02834

Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations

Published on Oct 6, 2021
Authors:
,
,

Abstract

Learning good representations on multi-relational graphs is essential to knowledge base completion (KBC). In this paper, we propose a new self-supervised training objective for multi-relational graph representation learning, via simply incorporating relation prediction into the commonly used 1vsAll objective. The new training objective contains not only terms for predicting the subject and object of a given triple, but also a term for predicting the relation type. We analyse how this new objective impacts multi-relational learning in KBC: experiments on a variety of datasets and models show that relation prediction can significantly improve entity ranking, the most widely used evaluation task for KBC, yielding a 6.1% increase in MRR and 9.9% increase in Hits@1 on FB15k-237 as well as a 3.1% increase in MRR and 3.4% in Hits@1 on Aristo-v4. Moreover, we observe that the proposed objective is especially effective on highly multi-relational datasets, i.e. datasets with a large number of predicates, and generates better representations when larger embedding sizes are used.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2110.02834
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2110.02834 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2110.02834 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2110.02834 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.